[OpenMP] Remove OpenMP CUDA Target Parallel compiler flag

[jhuber6]

Summary

The changes introduced in D97680 turns this command line option into a no-op so
it can be removed entirely.

Depends on D97680

[tianshilei1992]

LGTM

clang/include/clang/Basic/LangOptions.def

 LANGOPT(OpenMPIsDevice    , 1, 0, "Generate code only for OpenMP target device")
 LANGOPT(OpenMPCUDAMode    , 1, 0, "Generate code for OpenMP pragmas in SIMT/SPMD mode")
 LANGOPT(OpenMPIRBuilder   , 1, 0, "Use the experimental OpenMP-IR-Builder codegen path.")
 LANGOPT(OpenMPCUDAForceFullRuntime , 1, 0, "Force to use full runtime in all constructs when offloading to CUDA devices")
 LANGOPT(OpenMPCUDANumSMs  , 32, 0, "Number of SMs for CUDA devices.")
 LANGOPT(OpenMPCUDABlocksPerSM  , 32, 0, "Number of blocks per SM for CUDA devices.")
 LANGOPT(OpenMPCUDAReductionBufNum , 32, 1024, "Number of the reduction records in the intermediate reduction buffer used for the teams reductions.")
 LANGOPT(OpenMPOptimisticCollapse  , 1, 0, "Use at most 32 bits to represent the collapsed loop nest counter.")
-LANGOPT(OpenMPCUDATargetParallel, 1, 0, "Support parallel execution of target region on Cuda-based devices.")
 LANGOPT(RenderScript      , 1, 0, "RenderScript")
 
 LANGOPT(CUDAIsDevice      , 1, 0, "compiling for CUDA device")
 LANGOPT(CUDAAllowVariadicFunctions, 1, 0, "allowing variadic functions in CUDA device code")
 LANGOPT(CUDAHostDeviceConstexpr, 1, 1, "treating unattributed constexpr functions as __host__ __device__")
 LANGOPT(CUDADeviceApproxTranscendentals, 1, 0, "using approximate transcendental functions")
 LANGOPT(GPURelocatableDeviceCode, 1, 0, "generate relocatable device code")
 LANGOPT(GPUAllowDeviceInit, 1, 0, "allowing device side global init functions for HIP")

clang/include/clang/Driver/Options.td

def fopenmp_cuda_number_of_sm_EQ : Joined<["-"], "fopenmp-cuda-number-of-sm=">, Group<f_Group>,
   Flags<[CC1Option, NoArgumentUnused, HelpHidden]>;
 def fopenmp_cuda_blocks_per_sm_EQ : Joined<["-"], "fopenmp-cuda-blocks-per-sm=">, Group<f_Group>,
   Flags<[CC1Option, NoArgumentUnused, HelpHidden]>;
 def fopenmp_cuda_teams_reduction_recs_num_EQ : Joined<["-"], "fopenmp-cuda-teams-reduction-recs-num=">, Group<f_Group>,
   Flags<[CC1Option, NoArgumentUnused, HelpHidden]>;
 defm openmp_optimistic_collapse : BoolFOption<"openmp-optimistic-collapse",
   LangOpts<"OpenMPOptimisticCollapse">, DefaultFalse,
   PosFlag<SetTrue, [CC1Option]>, NegFlag<SetFalse>, BothFlags<[NoArgumentUnused, HelpHidden]>>;
-def fopenmp_cuda_parallel_target_regions : Flag<["-"], "fopenmp-cuda-parallel-target-regions">, Group<f_Group>,
-  Flags<[CC1Option, NoArgumentUnused, HelpHidden]>,
-  HelpText<"Support parallel execution of target regions on Cuda-based devices.">;
-def fno_openmp_cuda_parallel_target_regions : Flag<["-"], "fno-openmp-cuda-parallel-target-regions">, Group<f_Group>,
-  Flags<[NoArgumentUnused, HelpHidden]>,
-  HelpText<"Support only serial execution of target regions on Cuda-based devices.">;
 def static_openmp: Flag<["-"], "static-openmp">,
   HelpText<"Use the static host OpenMP runtime while linking.">;
 def fno_optimize_sibling_calls : Flag<["-"], "fno-optimize-sibling-calls">, Group<f_Group>;
 def foptimize_sibling_calls : Flag<["-"], "foptimize-sibling-calls">, Group<f_Group>;
 defm escaping_block_tail_calls : BoolFOption<"escaping-block-tail-calls",
   CodeGenOpts<"NoEscapingBlockTailCalls">, DefaultFalse,
   NegFlag<SetTrue, [CC1Option]>, PosFlag<SetFalse>>;
 def force__cpusubtype__ALL : Flag<["-"], "force_cpusubtype_ALL">;

clang/lib/Driver/ToolChains/Clang.cpp

case Driver::OMPRT_IOMP5:
         CmdArgs.push_back("-fopenmp-optimistic-collapse");
 
       // When in OpenMP offloading mode with NVPTX target, forward
       // cuda-mode flag
       if (Args.hasFlag(options::OPT_fopenmp_cuda_mode,
                        options::OPT_fno_openmp_cuda_mode, /*Default=*/false))
         CmdArgs.push_back("-fopenmp-cuda-mode");
 
-      // When in OpenMP offloading mode with NVPTX target, forward
-      // cuda-parallel-target-regions flag
-      if (Args.hasFlag(options::OPT_fopenmp_cuda_parallel_target_regions,
-                       options::OPT_fno_openmp_cuda_parallel_target_regions,
-                       /*Default=*/true))
-        CmdArgs.push_back("-fopenmp-cuda-parallel-target-regions");
-
       // When in OpenMP offloading mode with NVPTX target, check if full runtime
       // is required.
       if (Args.hasFlag(options::OPT_fopenmp_cuda_force_full_runtime,
                        options::OPT_fno_openmp_cuda_force_full_runtime,
                        /*Default=*/false))
         CmdArgs.push_back("-fopenmp-cuda-force-full-runtime");
       break;
     default:

clang/lib/Frontend/CompilerInvocation.cpp

#undef LANG_OPTION_WITH_MARSHALLING
   }
 
   if (!Opts.OMPHostIRFile.empty())
     GenerateArg(Args, OPT_fopenmp_host_ir_file_path, Opts.OMPHostIRFile, SA);
 
   if (Opts.OpenMPCUDAMode)
     GenerateArg(Args, OPT_fopenmp_cuda_mode, SA);
 
-  if (Opts.OpenMPCUDATargetParallel)
-    GenerateArg(Args, OPT_fopenmp_cuda_parallel_target_regions, SA);
-
   if (Opts.OpenMPCUDAForceFullRuntime)
     GenerateArg(Args, OPT_fopenmp_cuda_force_full_runtime, SA);
 
   // The arguments used to set Optimize, OptimizeSize and NoInlineDefine are
   // generated from CodeGenOptions.
 
   if (Opts.DefaultFPContractMode == LangOptions::FPM_Fast)
     GenerateArg(Args, OPT_ffp_contract, "fast", SA);
if (!llvm::sys::fs::exists(Opts.OMPHostIRFile))
       Diags.Report(diag::err_drv_omp_host_ir_file_not_found)
           << Opts.OMPHostIRFile;
   }
 
   // Set CUDA mode for OpenMP target NVPTX/AMDGCN if specified in options
   Opts.OpenMPCUDAMode = Opts.OpenMPIsDevice && (T.isNVPTX() || T.isAMDGCN()) &&
                         Args.hasArg(options::OPT_fopenmp_cuda_mode);
 
-  // Set CUDA support for parallel execution of target regions for OpenMP target
-  // NVPTX/AMDGCN if specified in options.
-  Opts.OpenMPCUDATargetParallel =
-      Opts.OpenMPIsDevice && (T.isNVPTX() || T.isAMDGCN()) &&
-      Args.hasArg(options::OPT_fopenmp_cuda_parallel_target_regions);
-
   // Set CUDA mode for OpenMP target NVPTX/AMDGCN if specified in options
   Opts.OpenMPCUDAForceFullRuntime =
       Opts.OpenMPIsDevice && (T.isNVPTX() || T.isAMDGCN()) &&
       Args.hasArg(options::OPT_fopenmp_cuda_force_full_runtime);
 
   // FIXME: Eliminate this dependency.
   unsigned Opt = getOptimizationLevel(Args, IK, Diags),
        OptSize = getOptimizationLevelSize(Args);